A new mixed‐effects regression model for the analysis of zero‐modified hierarchical count data

• Published in: Biometrical journal Vol. 63; no. 1; pp. 81 - 104
• Main Authors: Bertoli, Wesley, Conceição, Katiane S., Andrade, Marinho G., Louzada, Francisco
• Format: Journal Article
• Language: English
• Published: Germany Wiley - VCH Verlag GmbH & Co. KGaA 01.01.2021
• Subjects: Adaptive algorithms; approximate Bayesian inference; Bayesian analysis; Clustering; Competitiveness; Correlation analysis; Data structures; Datasets; Divergence; Empirical analysis; Heterogeneity; Mathematical models; mixed‐effects hurdle model; Monte Carlo simulation; overdispersion; Parameter estimation; Parameter sensitivity; Poisson distribution; Regression analysis; Regression models; repeated measures; Sensitivity analysis; Statistical analysis; Within-subjects design; zero‐modified count data; approximate Bayesian inference; mixed-effects hurdle model; overdispersion; zero-modified count data; Monte Carlo simulation; repeated measures
• DOI: 10.1002/bimj.202000046
• ISSN: 0323-3847; 1521-4036

Count data sets are traditionally analyzed using the ordinary Poisson distribution. However, such a model has its applicability limited as it can be somewhat restrictive to handle specific data structures. In this case, it arises the need for obtaining alternative models that accommodate, for example, (a) zero‐modification (inflation or deflation at the frequency of zeros), (b) overdispersion, and (c) individual heterogeneity arising from clustering or repeated (correlated) measurements made on the same subject. Cases (a)–(b) and (b)–(c) are often treated together in the statistical literature with several practical applications, but models supporting all at once are less common. Hence, this paper's primary goal was to jointly address these issues by deriving a mixed‐effects regression model based on the hurdle version of the Poisson–Lindley distribution. In this framework, the zero‐modification is incorporated by assuming that a binary probability model determines which outcomes are zero‐valued, and a zero‐truncated process is responsible for generating positive observations. Approximate posterior inferences for the model parameters were obtained from a fully Bayesian approach based on the Adaptive Metropolis algorithm. Intensive Monte Carlo simulation studies were performed to assess the empirical properties of the Bayesian estimators. The proposed model was considered for the analysis of a real data set, and its competitiveness regarding some well‐established mixed‐effects models for count data was evaluated. A sensitivity analysis to detect observations that may impact parameter estimates was performed based on standard divergence measures. The Bayesian p‐value and the randomized quantile residuals were considered for model diagnostics.